Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation profile is known; the description goes further by disclosing that the old answer is retained as an earlier version and drops out of the conversation, plus the blocking behavior ("waits like send_message"). The cross-tool reference for waiting is slightly indirect and nothing is said about permissions or failure output, so it stops short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The two-mode choice is front-loaded and every clause carries information (scope limits, preconditions, remedy, blocking). It is dense to the point of being telegraphic — stacked dashes, semicolons and parentheses — which costs a little readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a state-mutating regeneration tool with no output schema, the description covers preconditions, side effects on prior versions, and blocking behavior well. It never states what the call returns (the new turn, presumably), which is a modest gap given there is no output schema to lean on.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented (baseline 3). The description adds meaning beyond the schema by explaining the consequence of each mode: omitting message regenerates, supplying message replaces the words and lets the agent answer the edit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource — regenerate the conversation's LATEST message, or replace its words — and explicitly separates the two modes. It is clearly distinguishable from siblings like send_message, apply_turn, and undo_turn because it constrains itself to the latest message only.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when/when-not conditions: only your own message, only the latest one, never while it is running, and refused while external changes are still in place — with the remedy named (undo_turn it and its reviews first). That is a full routing rule set, including the alternative tool to use first.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.